Bill Image OCR Matching for Fast Mobile Payee Onboarding
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems struggle with efficiently adding new payees to financial institution accounts via mobile devices due to the lack of standardized formats in paper bills, making it difficult for customers to know where to focus their camera when capturing images for payee identification.
Innovation Solution
A system and method that utilizes optical character recognition to extract and compare blocks of text from captured bill images against a payee database, allowing for automatic payee identification and account number extraction, with manual entry as a fallback for non-matching cases.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual payee information input is required, then payee identification accuracy is improved, but user operation time and complexity increase
Solution Approach 1:
The system automatically extracts payee information from bill images using OCR technology and matches it against the payee database without requiring manual user input. The mobile device captures the bill image, the server processes the text extraction and payee matching, and automatically adds the payee to the user's account, eliminating the need for users to manually type payee details.
Solution Approach 2:
The patent replaces the mechanical process of manual typing and form filling with automated optical character recognition and database matching systems. The OCR engine extracts text from the captured bill image, and the payee matching algorithm automatically compares this extracted information against the stored payee database to identify and add the correct payee.
2Reliability
If manual payee information input is required, then payee identification reliability is improved, but device operation complexity increases
Solution Approach 1:
The system performs self-service by automatically capturing the bill image through the device camera, extracting the payee information via OCR, matching it against the payee database, and completing the payee addition process without requiring the user to navigate complex forms or manually input data, thereby maintaining reliability while simplifying operation.
Solution Approach 2:
The patent introduces an intermediary OCR processing system that acts as a bridge between the captured bill image and the payee database. This intermediary automatically extracts and structures the payee information, transforming the unstructured image data into a format suitable for database matching, thereby reducing the operational complexity for the user while maintaining identification reliability.
3Productivity
If standardized bill formats are assumed, then processing speed is improved, but adaptability to different bill formats deteriorates
Solution Approach 1:
The patent employs parameter changes by adjusting the OCR recognition parameters and text extraction algorithms to adapt to different bill formats. The system can dynamically modify its text extraction patterns, field identification rules, and data structure expectations to accommodate various bill layouts from different payees, thereby maintaining both processing speed and format adaptability.
Data Source
AI summary
A provider computing system associated with a provider institution includes a network interface configured to communicate data over a network, and a processing circuit. The processing circuit is configured to receive, by the network interface, image data from a user computing device associated with a user, the image data pertaining to a bill of a user issued by a payee, scan the user computing device for tokens, transform the image data from a non-standardized format into computer-readable data, extract a data structure from the computer-readable data based on identified data from the bill of the user, identify the payee from the payee database based on determining a match level meets a threshold, and add the payee to an account of the user to enable authorization of a payment to the payee via the user computing device.